燃气轮机异常检测技术研究进展

Latest Research Findings in the Study of the Anomaly Detection Technologies for Gas Turbine

考虑燃气轮机结构组成复杂、旋转部件服役环境恶劣以及多类型故障容易耦合等特点,如何提高系统/设备的异常检测性能是实现燃气轮机状态监测与健康维护的关键。本文概述了燃气轮机异常检测技术的发展历程,分别从气路性能参数、振动参数、油液分析/静电监测、多源信息融合等方面综述了燃气轮机异常检测方法的国内外研究进展。在此基础上,针对目前研究存在的问题与不足,从有效提高建模精度、解决气路分析方程欠定问题、丰富异常特征数据库、增加数据源信息、强化多源信息融合模式和深度挖掘隐含信息等多个角度展望了燃气轮机异常检测技术的发展方向。

In view of such specific features as complex in the structure of gas turbines,very bad in service environments of the rotating parts or components and easy for numerous types of faults to be coupled etc.,how to enhance the anomaly detection performance of systems/equipment items becomes the key to realizing the condition monitoring and health maintenance of a gas turbine. The development history of the anomaly detection technologies for gas turbines was briefly described and advances in the study of the anomaly detection methods both in domestics and abroad for gas turbines were given in a comprehensive way from the following aspects: parameters relating to the performance of gas paths,vibration parameters,oil liquid analysis/static monitoring and multiple source information etc. On this basis,in the light of the problems and demerits now existing in the research work,the future development prospects of the anomaly detection technologies for gas turbines were given from various points of view: to effectively enhance the modeling precision,solve the problems underdetermined in the equations for analyzing the gas paths,enrich the anomaly characteristic database,add more information to the data sources,strengthen the fusion mode of multiple source information and deeply mine the implicit information etc.